Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2169 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.4304. Min Act: -0.1700
Data Index: 5826187 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.2578. Min Act: -0.1700
Data Index: 1741064 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.2578. Min Act: -0.1700
Data Index: 8769072 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.2578. Min Act: -0.1700
Data Index: 3264263 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.2578. Min Act: -0.1700
Data Index: 6689936 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.2106. Min Act: -0.1700
Data Index: 3958589 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.2263. Min Act: -0.1700
Data Index: 1504950 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.2263. Min Act: -0.1700
Data Index: 5284452 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.2263. Min Act: -0.1700
Data Index: 2525331 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.1949. Min Act: -0.1700
Data Index: 8185367 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.2263. Min Act: -0.1700
Data Index: 686346 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.2106. Min Act: -0.1700
Data Index: 2005470 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.2106. Min Act: -0.1700
Data Index: 7749015 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.1792. Min Act: -0.1700
Data Index: 5980974 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.1792. Min Act: -0.1700
Data Index: 646783 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.1477. Min Act: -0.1700
Data Index: 8121214 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.1634. Min Act: -0.1700
Data Index: 4731038 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.1634. Min Act: -0.1700
Data Index: 6435006 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.1634. Min Act: -0.1700
Data Index: 1872628 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.1949. Min Act: -0.1700
Data Index: 7002454 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #19